Project information

Retrieval Augmented Generation (RAG) with LangChain and OpenAI

This project implements the RAG framework using OpenAI's models and LangChain's Python library.

The main focus of this project are:

  1. Document splitting
  2. Vector embedding
  3. Vector database
  4. Semantic search (similarity, maximum marginal relevance, self-query)
  5. Retrieval chains